VoiceStudio

Free · github.com

Open-source, fully local text-to-speech suite for voice cloning, dubbing, transcription and audiobooks, with desktop apps.

Best for: Use it when you want ElevenLabs-style voice cloning, dubbing and transcription running offline on your own machine.

Free tier
Open-source repo, runs locally; no paid tier mentioned
Works as
Open source, Self-hostable, Mac, Windows, Linux, No sign-up
Tags
voicestudio, voice, design, video, audiobook, voice cloning, text to speech, tts, dubbing, transcription, dictation, audio generation, self-hosted, open source, elevenlabs alternative

Visit github.com ↗

Similar tools

  • Fish Audio Freemium · fish.audio
    Text-to-speech and voice cloning.
  • Inworld Freemium · inworld.ai
    Realtime voice and character AI for apps and games.
  • ComfyUI Free · comfy.org
    Node-based open-source diffusion workflows, local or cloud.

More in Image, video & audio generation

  • Higgsfield Freemium · higgsfield.ai
    Cinematic AI video with camera-move presets, plus image and character tools.
  • Motion Paid · motion.so
    Text-to-video agent for launches, demos and ads.
  • HeyGen Freemium · heygen.com
    AI avatar videos, dubbing and translation.
  • Krea Freemium · krea.ai
    Real-time image generation, enhancing and video in one studio.
  • Recraft Freemium · recraft.ai
    Image generation that's actually good at vectors, logos and brand consistency.
  • Ideogram Freemium · ideogram.ai
    Image model that nails text in images.

All image, video & audio generation →